R Notebook

source('../settings/settings.R')
source('commonFunctions.R')

drive1 <- read.csv('../data/processed/analysis/TT1_Drive_1_PP.csv')
drive2 <- read.csv('../data/processed/Analysis/TT1_Drive_2_PP.csv')
drive3 <- read.csv('../data/processed/Analysis/TT1_Drive_3_PP.csv')
drive4 <- read.csv('../data/processed/Analysis/TT1_Drive_4_PP.csv', stringsAsFactors = T)

set.seed(43)
combinedDf <- cbind(drive4, 
                    drive1$MeanPP_Seg0, 
                    drive2$MeanPP_SegMax, drive3$MeanPP_SegMax, 
                    drive2$MeanPP_Seg0, drive3$MeanPP_Seg0,
                    drive2$StdPP, drive3$StdPP 
                  )
names(combinedDf) <- c(names(drive4), 
                       "PP_Dev_1_Turning",
                       "PP_Dev_2_Straight", "PP_Dev_3_Straight", 
                       "PP_Dev_2_Turning", "PP_Dev_3_Turning", 
                       "Std_PP_2", "Std_PP_3")

combinedDf$Subject <- paste0("#", str_pad(combinedDf$Subject, 2, pad="0"))

combinedDf_NoStressor <- combinedDf[combinedDf$Activity == "NO",]
combinedDf_Cognitive <- combinedDf[combinedDf$Activity == "C",]
combinedDf_Motoric <- combinedDf[combinedDf$Activity == "M",]

combinedDf_NoStressor$Subject <- as.factor(combinedDf_NoStressor$Subject)
combinedDf_Cognitive$Subject <- as.factor(combinedDf_Cognitive$Subject)
combinedDf_Motoric$Subject <- as.factor(combinedDf_Motoric$Subject)

COLOR_NORMAL <- list(color='rgb(120,120,120)')
COLOR_COGNITIVE <- list(color='rgb(158,202,225)')
COLOR_MOTORIC <- list(color='rgb(58,200,225)')
COLOR_FAILURE <- list(color='red')

yAxis <- list(
  title = 'Perinasal Perspiration (Log)',
  range=c(-0.3, 0.5)
)

THRESHOLD_MILD = 0.07
THRESHOLD_EXTREME = 0.2

MARKER_LINE_MILD = list(color="blue")
MARKER_LINE_EXTREME = list(color="red")

fig_NoStressor <- plot_ly(combinedDf_NoStressor, x = ~Subject, y = ~PP_Dev_2_Straight, type = 'bar', name = 'Cognitive - Mean PP (Straight)', marker=COLOR_COGNITIVE) %>%
  add_trace(y = ~PP_Dev_3_Straight, name = 'Motoric - Mean PP (Straight)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev_2_Turning, name = 'Cognitive - Mean PP (Turning)', marker=COLOR_COGNITIVE) %>% 
  add_trace(y = ~PP_Dev_3_Turning, name = 'Motoric - Mean PP (Turning)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev, name = 'Failure - PP Deviation', marker=COLOR_FAILURE) %>% 
  add_segments(x="#01", xend="#41", y = THRESHOLD_MILD, yend = THRESHOLD_MILD, name="Threshold: Mild Change of PP",
                           line=list(color="blue", dash = 'dot')) %>%
  # add_segments(x="#01", xend="#41", y = THRESHOLD_EXTREME, yend = THRESHOLD_EXTREME, name="Threshold: Extreme Change of PP",
  #                          line=list(color="darkred", dash = 'dot')) %>%
  layout(yaxis = yAxis, barmode = 'group', title="Failure Driving \n Group=No Stressor")

htmltools::tagList(fig_NoStressor)

A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...

fig_Cognitive <- plot_ly(combinedDf_Cognitive, x = ~Subject, y = ~PP_Dev_2_Straight, type = 'bar', name = 'Cognitive - Mean PP (Straight)', marker=COLOR_COGNITIVE) %>%
  add_trace(y = ~PP_Dev_3_Straight, name = 'Motoric - Mean PP (Straight)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev_2_Turning, name = 'Cognitive - Mean PP (Turning)', marker=COLOR_COGNITIVE) %>% 
  add_trace(y = ~PP_Dev_3_Turning, name = 'Motoric - Mean PP (Turning)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev, name = 'Failure - PP Deviation', marker=COLOR_FAILURE) %>% 
  add_segments(x="#02", xend="#22", y = THRESHOLD_MILD, yend = THRESHOLD_MILD, name="Threshold: Mild Change of PP",
                           line=list(color="blue", dash = 'dot')) %>%
  # add_segments(x="#02", xend="#22", y = THRESHOLD_EXTREME, yend = THRESHOLD_EXTREME, name="Threshold: Extreme Change of PP",
  #                          line=list(color="darkred", dash = 'dot')) %>%
  layout(yaxis = yAxis, barmode = 'group', title="Failure Driving \n Group=Cognitive")

htmltools::tagList(fig_Cognitive)

A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...

fig_Motoric <- plot_ly(combinedDf_Motoric, x = ~Subject, y = ~PP_Dev_2_Straight, type = 'bar', name = 'Cognitive - Mean PP (Straight)', marker=COLOR_COGNITIVE) %>%
  add_trace(y = ~PP_Dev_3_Straight, name = 'Motoric - Mean PP (Straight)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev_2_Turning, name = 'Cognitive - Mean PP (Turning)', marker=COLOR_COGNITIVE) %>% 
  add_trace(y = ~PP_Dev_3_Turning, name = 'Motoric - Mean PP (Turning)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev, name = 'Failure - PP Deviation', marker=COLOR_FAILURE) %>% 
  add_segments(x="#05", xend="#31", y = THRESHOLD_MILD, yend = THRESHOLD_MILD, name="Threshold: Mild Change of PP",
                           line=list(color="blue", dash = 'dot')) %>%
  # add_segments(x="#05", xend="#31", y = THRESHOLD_EXTREME, yend = THRESHOLD_EXTREME, name="Threshold: Extreme Change of PP",
  #                          line=list(color="darkred", dash = 'dot')) %>%
  layout(yaxis = yAxis, barmode = 'group', title="Failure Driving \n Group: Motoric")

htmltools::tagList(fig_Motoric)

A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...

library(nlme)
combinedDf$Subject = as.factor(combinedDf$Subject)
combinedDf$Activity = as.factor(combinedDf$Activity)
combinedDf$PP_Dev_Group = ifelse(combinedDf$PP_Dev > THRESHOLD_MILD, 1, 0)

model = lme(PP_Dev ~ 
              abs(PP_Dev_2_Straight)
              + abs(PP_Dev_3_Straight)
              + abs(PP_Dev_2_Turning) 
              + abs(PP_Dev_3_Turning)
              + factor(Activity), 
            random=~1|Subject,
            data=combinedDf,
            method="REML")

# anova(model)
summary(model)

Linear mixed-effects model fit by REML
 Data: combinedDf 

Random effects:
 Formula: ~1 | Subject
        (Intercept)   Residual
StdDev:  0.06029036 0.02260888

Fixed effects: PP_Dev ~ abs(PP_Dev_2_Straight) + abs(PP_Dev_3_Straight) + abs(PP_Dev_2_Turning) +      abs(PP_Dev_3_Turning) + factor(Activity) 

 Correlation: 
                       (Intr) a(PP_D_2_S a(PP_D_3_S a(PP_D_2_T a(PP_D_3_T fc(A)M
abs(PP_Dev_2_Straight)  0.627                                                   
abs(PP_Dev_3_Straight)  0.041  0.045                                            
abs(PP_Dev_2_Turning)  -0.509 -0.788     -0.427                                 
abs(PP_Dev_3_Turning)  -0.561 -0.477     -0.717      0.525                      
factor(Activity)M      -0.487 -0.222      0.303     -0.084     -0.024           
factor(Activity)NO     -0.257 -0.044      0.547     -0.313     -0.341      0.600

Standardized Within-Group Residuals:
        Min          Q1         Med          Q3         Max 
-0.46048178 -0.28553137  0.03655763  0.12903557  0.67575137 

Number of Observations: 21
Number of Groups: 21 

plot(model)

combinedDf$PP_Dev <- NULL

combinedDf$Subject <- NULL
combinedDf$Activity_NO <- ifelse(combinedDf$Activity == "NO", 1, 0)
combinedDf$Activity_C <- ifelse(combinedDf$Activity == "C", 1, 0)
combinedDf$Activity_M <- ifelse(combinedDf$Activity == "M", 1, 0)
combinedDf$Activity <- NULL

combinedDf$Class <- ifelse(combinedDf$PP_Dev_Group == 1, T, F)
combinedDf$PP_Dev_Group <- NULL

# library(mefa)
# combinedDf <- rep(combinedDf, 10) 

n_folds <- 3
params <- param <- list(objective       = "binary:logistic", 
               booster          = "gbtree",
               eval_metric      = "auc",
               eta              = 0.1,
               max_depth        = 8,
               alpha            = 1,
               lambda           = 0,
               gamma            = 0.3,
               min_child_weight = 0.3,
               subsample        = 1,
               colsample_bytree = 0.5)
           
# XGBoost Model         
xgb_m <- xgb.cv(   params               = param,
                  data = as.matrix(combinedDf %>% select(-Class)) ,
                  label =  combinedDf$Class,
                  nrounds             = 500,
                  verbose             = F,
                  prediction          = T,
                  maximize            = T,
                  nfold               = n_folds,
                  metrics             = c("auc", "error"),
                  early_stopping_rounds = 100,
                  stratified            = F,
                  scale_pos_weight      = 3.05)

# xgb_m$evaluation_log[xgb_m$best_iteration,"test_auc_mean"]
xgb_m$evaluation_log[xgb_m$best_iteration,]

NA

library(pROC)

# it = which.max(xgb_m$evaluation_log$test_auc_mean)
# best.iter = xgb_m$evaluation_log$iter[it]
# best.iter 

plot(pROC::roc(response = ifelse(combinedDf$Class==T, 1, 0),
               predictor = xgb_m$pred,
               levels=c(0, 1)),
     lwd=1.5) 

Setting direction: controls < cases